---
title: "Analysis 3_Amber.C, Chujun.C, Wenxiao.Z"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: fill
    social: [ "twitter", "facebook", "menu"]
    source_code: embed
---

```{r setup, include=FALSE}
library(flexdashboard)
library(knitr)
library(DT)
library(rpivotTable)
library(ggplot2)
library(plotly)
library(dplyr)
library(openintro)
library(highcharter)
library(ggvis)
```


```{r}
on <- read.csv("/Users/amber/Downloads/On_Time_50.csv")
```

```{r}
mycolors <- c("blue", "#FFC125", "darkgreen", "darkorange")
```

Interactive Data Visualization
=====================================
Row
---------------------------------------

### Delay Analysis
```{r}
valueBox(paste("Delay minutes"),
         color = "warning")
```

### Maximum Arrival Delay Minutes

```{r}
valueBox(max(on$ArrDelayMinutes,na.rm = TRUE),
         icon = "fa-plane-arrival")
```

### Maximum Departure Delay Minutes
```{r}
valueBox(max(on$DepDelayMinutes,na.rm = TRUE),
         icon = "fa-plane-departure")
```

### Average Delay Minute before Cancellation
```{r}
cancel1 <- subset(on,Cancelled==1)
valueBox(mean(cancel1$DepDelayMinutes,na.rm = TRUE),
         icon = "fa-window-close")
```

Row
---------------------------------------
### Departure Delay ~ Arrival Delay
```{r}
dep.arr <- ggplot(data=on, aes(x=DepDelay, y=ArrDelay)) + geom_point(size = 1, alpha = 0.2, shape = 16) + geom_abline(color = "#0492c2") + xlim(c(-40,400)) + ylim(c(-70,400)) + xlab("Departure Delay") + ylab("Arrival Delay")
dep.arr + labs(title = "Departure Delay Minute ~ Arrival Delay Minute")
```

### Departure Delay by Departure Time
```{r}
b <- ggplot(aes(x=DepTimeBlk, y=DepDelayMinutes),data = on) +
  geom_point(size=1,alpha=0.5) + ylim(0,850)
b + theme(axis.text.x = element_text(angle=90, hjust=1, vjust=.5)) + labs(title="Departure Delay by Departure Time")
```

Row
---------------------------------------

### Delay Reason
```{r}
num <- c(141572,11183,112638,442,196226)
percentlabels<- round(100*num/sum(num), 1)
pielabels<- paste(percentlabels, "%", sep="")
cols <- c("#f66d44","#feae65","#e6f69d","#aadea7","#2d87bb")
pie(num, main="Delay Reason",labels=pielabels,col = cols, cex=0.8)
legend("bottomright",c("Carrier Delay","Weather Delay","NAS Delay","Security Delay","LateAircraft Delay"),fill=cols, cex=0.8)
```

### Average Delay Time By Delay Reason
```{r}
attach(on)
c <- sum(CarrierDelay,na.rm = TRUE)
c1 <- as.numeric (length(which(CarrierDelay!=0)))
w <- sum(WeatherDelay,na.rm = TRUE)
w1 <- as.numeric (length(which(WeatherDelay!=0)))
n <- sum(NASDelay,na.rm = TRUE)
n1 <- as.numeric (length(which(NASDelay!=0)))
s <- sum(SecurityDelay,na.rm = TRUE)
s1 <- as.numeric (length(which(SecurityDelay!=0)))
l <- sum(LateAircraftDelay,na.rm = TRUE)
l1 <- as.numeric (length(which(LateAircraftDelay!=0)))
avg <- c(c/c1,w/w1,n/n1,s/s1,l/l1)
avg1 <- data.frame(c("CarrierDelay","WeatherDelay","NASDelay","SecurityDelay","LateAircraftDelay"),avg[1:5])
colnames(avg1) <- c("reason","minute")
ggplot(avg1,aes(x=reason,y=minute))+geom_col(fill="#f66d44",width = 0.5)+geom_text(aes(x=reason,y=minute,label=format(avg1$minute,digits = 3))) + ggtitle("Average Delay Time By Delay Reason")
```


Interactive Data Visualization II.
=====================================
Row
---------------------------------------
### Carrier Most Likely to Delay
```{r}
valueBox(paste("Envoy Air (MQ): 23.02%"),
         icon = "fa-tired")
```

Row
---------------------------------------

### Total Flights By Carrier
```{r}
number.carrier <- on %>% group_by(UniqueCarrier) %>% summarize(Count = n())

ggplot(data=number.carrier, aes(x=UniqueCarrier, y=Count)) + geom_col(colour="black", fill="#fad0c9ff") + geom_text(aes(label = Count), size = 3) + ggtitle("Total Flights by Carrier") + scale_fill_manual(values = c("red", "green", "blue")) + theme(legend.position="none") + coord_flip() 
```

### Departure Delay Minutes by Carrier
```{r}
hcboxplot(on$DepDelay, on$UniqueCarrier) %>% hc_yAxis(max=100) %>% hc_title(text="Departure Delay Minute By Carrier")
```


Map
========================================
Row
----------------------------------------

###Origin State Distribution
```{r}
on$DepDelayMinutes[is.na(on$DepDelayMinutes)] <- 0
delaymin_orign<-aggregate(on$DepDelayMinutes, by=list(OriginStateName=on$OriginStateName), FUN=sum)
library(highcharter)
library(openintro)
highchart() %>% 
  hc_add_series_map(usgeojson,delaymin_orign, 
                    name='OriginStateName',
                    value='x', 
                    joinBy = c('woename','OriginStateName')) %>% 
  hc_title(text = 'Origin State') %>% 
  hc_mapNavigation(enabled =T)
```

Row
-----------------------------------
### Destination State Distribution
```{r}
delaymin_dest<-aggregate(on$DepDelayMinutes, by=list(DestStateName=on$DestStateName), FUN=sum)
library("viridisLite")
highchart() %>% 
  hc_add_series_map(usgeojson,delaymin_dest, 
                    name='DestStateName',
                    value='x', 
                    joinBy = c('woename','DestStateName')) %>% 
  hc_title(text = 'Destination State') %>% 
  hc_mapNavigation(enabled =T)
```



Data Table
========================================

```{r}
delaydata<- subset(on,DepDelay >= 0)
datatable(delaydata,
          caption = "Delay Data",
          rownames = T,
          filter = "top",
          options = list(pageLength = 25))
```

Pivot Table
=========================================

```{r}
rpivotTable(on,
            aggregatorName = "Count",
            cols= "DestStateName",
            rows = "OriginStateName",
            rendererName = "Heatmap")
```

Summary {data-orientation=columns}
=========================================

Column
-----------------------------------------

### Average Departure Delay Minute
```{r}
valueBox(mean(on$DepDelayMinutes),
         icon = "fa-plane-departure")
```



### Average Arrival Delay Minute
```{r}
valueBox(mean(on$ArrDelayMinutes,na.rm = TRUE, digits = 3),
         icon = "fa-plane-arrival")
```





### Carrier Most Likely to Delay: Envoy Air (23%)
```{r}
valueBox(paste("Envoy Air (MQ): 23.02%"),
         icon = "fa-tired")
```






### Cancellation Rate
```{r}
valueBox(paste("1.06%"),
         icon = "fa-window-close")
```


Column
-----------------------------------


Report

* This is a report on `r length(on$FlightNum)` flights.

* The average departure delay minute was `r mean(on$DepDelayMinutes)` minutes.

* The average arrival delay minute was `r mean(on$ArrDelayMinutes,na.rm=TRUE)` minutes.

* Envoy Air(MQ) had the highest possibility of departure delay of 23.02%.

* Cancellation Rate was 1.06%.

This report was generated on `r format(Sys.Date(), format = "%B %d, %Y")`.